LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912303703654400 |
|---|---|
| author | Sadruddin, Sameer D'Souza, Jennifer Poupaki, Eleni Watkins, Alex Giglou, Hamed Babaei Rula, Anisa Karasulu, Bora Auer, Sören Mackus, Adrie Kessels, Erwin |
| author_facet | Sadruddin, Sameer D'Souza, Jennifer Poupaki, Eleni Watkins, Alex Giglou, Hamed Babaei Rula, Anisa Karasulu, Bora Auer, Sören Mackus, Adrie Kessels, Erwin |
| contents | Extracting structured information from unstructured text is crucial for modeling real-world processes, but traditional schema mining relies on semi-structured data, limiting scalability. This paper introduces schema-miner, a novel tool that combines large language models with human feedback to automate and refine schema extraction. Through an iterative workflow, it organizes properties from text, incorporates expert input, and integrates domain-specific ontologies for semantic depth. Applied to materials science--specifically atomic layer deposition--schema-miner demonstrates that expert-guided LLMs generate semantically rich schemas suitable for diverse real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00752 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models Sadruddin, Sameer D'Souza, Jennifer Poupaki, Eleni Watkins, Alex Giglou, Hamed Babaei Rula, Anisa Karasulu, Bora Auer, Sören Mackus, Adrie Kessels, Erwin Computation and Language Artificial Intelligence Digital Libraries Extracting structured information from unstructured text is crucial for modeling real-world processes, but traditional schema mining relies on semi-structured data, limiting scalability. This paper introduces schema-miner, a novel tool that combines large language models with human feedback to automate and refine schema extraction. Through an iterative workflow, it organizes properties from text, incorporates expert input, and integrates domain-specific ontologies for semantic depth. Applied to materials science--specifically atomic layer deposition--schema-miner demonstrates that expert-guided LLMs generate semantically rich schemas suitable for diverse real-world applications. |
| title | LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models |
| topic | Computation and Language Artificial Intelligence Digital Libraries |
| url | https://arxiv.org/abs/2504.00752 |